# Maximum Spanning Trees Are Invariant to Temperature Scaling in Graph-based Dependency Parsing

arXiv: https://arxiv.org/abs/2106.08159 · HTML: https://mlsanity.com/paper/2106.08159/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 2 of its 4 references that are in the map.
- First posted on arXiv 15 Jun 2021.

## Builds on (most cited first, 2 of 2)

- [On Calibration of Modern Neural Networks](https://mlsanity.com/paper/1706.04599/) (2017)
- [Please Mind the Root: Decoding Arborescences for Dependency Parsing](https://mlsanity.com/paper/2010.02550/) (2020)

## Abstract (arXiv)

Modern graph-based syntactic dependency parsers operate by predicting, for each token within a sentence, a probability distribution over its possible syntactic heads (i.e., all other tokens) and then extracting a maximum spanning tree from the resulting log-probabilities. Nowadays, virtually all such parsers utilize deep neural networks and may thus be susceptible to miscalibration (in particular, overconfident predictions). In this paper, we prove that temperature scaling, a popular technique for post-hoc calibration of neural networks, cannot change the output of the aforementioned procedure. We conclude that other techniques are needed to tackle miscalibration in graph-based dependency parsers in a way that improves parsing accuracy.